
import warnings
warnings.filterwarnings("ignore")

import pandas as pd
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import LSTM, Dense, Embedding
import tensorflow
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.cluster import KMeans
from sklearn.decomposition import PCA
import numpy as np 
import pandas as pd 
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import linear_kernel, cosine_similarity
from sklearn.utils import gen_batches
import networkx as nx
import matplotlib.pyplot as plt
import re
import numpy as np
from IPython.display import display
from matplotlib import pyplot as plt
from wordcloud import WordCloud
import seaborn as sns
import json


# Importing data set
df = pd.read_csv("recipes_data.csv")
df.head(5)


df.columns.tolist()

['title', 'ingredients', 'directions', 'link', 'source', 'NER', 'site']


# Converting from json to array and then to numpy array
df["NER"] = df["NER"].apply(lambda x: np.array(json.loads(x)))


# Assuming your DataFrame is named "df"
df['directions'] = df['directions'].apply(eval)  # Convert directions column to list type


df['No_of_Steps_to_make_recipe'] = df['directions'].apply(lambda x: len(x))
df.head(5)


df['ingredients'] = df['ingredients'].apply(eval)  # Convert directions column to list type


df['No_of_ingredients_in_recipe'] = df['ingredients'].apply(lambda x: len(x))
df.head(5)


df.sort_values(by='No_of_ingredients_in_recipe')


df.sort_values(by='No_of_Steps_to_make_recipe')


# Check for missing values in the dataset
missing_values = df.isnull().sum()
missing_values

title                          0
ingredients                    0
directions                     0
link                           0
source                         0
NER                            0
site                           0
No_of_Steps_to_make_recipe     0
No_of_ingredients_in_recipe    0
dtype: int64


# Check the data types of columns in the dataset
data_types = df.dtypes
data_types

title                          object
ingredients                    object
directions                     object
link                           object
source                         object
NER                            object
site                           object
No_of_Steps_to_make_recipe      int64
No_of_ingredients_in_recipe     int64
dtype: object


# Check unique values in a specific column
for c in df.columns:
    try:
        unique_values = df[c].nunique()
    except:
        continue
    print(c, " has ",unique_values, " values ")

title  has  1312871  values 
link  has  2231142  values 
source  has  2  values 
site  has  28  values 
No_of_Steps_to_make_recipe  has  127  values 
No_of_ingredients_in_recipe  has  81  values


plt.figure(figsize=(16, 6))
sns.boxplot(x=df['No_of_ingredients_in_recipe'])
plt.show()


df['No_of_ingredients_in_recipe'].min(), df['No_of_ingredients_in_recipe'].mean(), df['No_of_ingredients_in_recipe'].max()

(1, 8.727042474212757, 407)


max_ingredients = df[df['No_of_ingredients_in_recipe'] == df['No_of_ingredients_in_recipe'].max()]
max_ingredients


max_ingredients.values

array([["Grandma'S Chicken Fricassee",
        list(['1 lb. chopped meat', '1 egg', '1/2 c. seasoned bread crumbs', '2 Tbsp. ketchup', '1 tsp. salt', '1/2 tsp. pepper', '6 to 7 potatoes (medium)', '2 1/2 lb. ham end', '1 c. milk', '4 Tbsp. seasoned bread crumbs', '4 Tbsp. butter', '1 lb. ham steak, cubed', '2 c. celery, sliced', '3/4 c. mayonnaise', '1 can chunky chicken soup', '2 Tbsp. lemon juice', '3 eggs, hard-boiled and cut up', '1 (8 oz.) can mushroom stems and pieces', '1 c. walnuts', '1/2 c. butter', '2 c. stuffing mix', '12 oz. corn bread twists', '1 lb. ground ham', '1 can Cheddar cheese soup', '1 c. seasoned bread crumbs', '1 pkg. onion soup mix', '4 Tbsp. butter, divided', '4 Tbsp. flour, divided', '2 tsp. seasoned salt, divided', '2 to 2 1/2 lb. boneless veal', '1 Tbsp. paprika, divided', '1 can chicken broth', '1/2 lb. mushrooms, sliced', '2 medium onions, sliced', '1/4 c. steak sauce', 'hot buttered noodles', '1 roast beef (with or without bones, any size)', '8 oz. ditalini macaroni', '1 (15 oz.) can garbanzo beans', '2 c. cooked chicken, cubed', '8 oz. sour cream', '5 oz. Cheddar cheese soup', '1 tsp. oregano', '1 tsp. garlic powder', '1/2 tsp. seasoned salt', '1/2 tsp. black pepper', '1/2 tsp. soy sauce', '2 to 3 lb. meat loaf mix (1 lb. beef, 1/2 lb. pork and 1/2 lb. veal)', '2 to 3 eggs', '1 c. Italian style bread crumbs', '1/2 c. grated Parmesan cheese', '1 Tbsp. oregano', 'spaghetti sauce', '1 lb. sweet Italian sausage (optional)', '1 1/2 c. instant rice', '1 can chicken broth', '1 lb. shrimp', '1 lb. smoked sausage (link)', '1 c. green pepper, cut in medium pieces', '1 c. celery, sliced diagonally', '1 c. onions, cut fine', '1 (1 lb.) can stewed tomatoes, cut into pieces', '2 cans condensed tomato soup', '6 to 8 drops hot pepper sauce', '1/2 tsp. black pepper', '1 tsp. seasoned salt', '1 tsp. garlic powder', '1 1/2 lb. bulk sweet sausage', '1 (32 oz.) jar spaghetti sauce', '1 can condensed cream of tomato soup', '1 green pepper, cut into small pieces', '1 medium onion, diced fine', '6 lasagne noodles', '1 small eggplant', '4 to 6 Tbsp. olive oil', '1 c. grated Parmesan cheese, divided', '1/4 lb. Mozzarella cheese, sliced thin', '1 medium head cabbage', '1 tsp. salt', '1/2 tsp. pepper', '2 lb. meat loaf mix', '2 pkg. onion soup mix', '1/2 c. instant rice', '2 cans condensed tomato soup', '2 cans water', '1 lb. meat loaf mix (beef, pork and veal)', '1/2 medium onion, chopped fine', '1/2 c. seasoned bread crumbs', '1 egg', '1/4 c. Parmesan cheese, grated', '1/4 c. milk', '1/2 tsp. garlic powder', '1/2 tsp. seasoned salt', '1/4 tsp. pepper', '1 Tbsp. olive oil', '1 jar chicken gravy', '1 c. sour cream', '1 Tbsp. paprika', '1 1/2 lb. ground chuck', '1 c. seasoned bread crumbs', '1 egg', '2 green onions, cut small', '1/2 c. spaghetti sauce', '1/4 tsp. black pepper', '1 (16 oz.) cream-style corn', '1 pkg. Knorr onion soup mix', '6 large green peppers or 8 medium', '1 1/4 lb. ground lamb', '2 c. instant rice (uncooked)', '1 can cream of mushroom soup', '1 (2.62 oz.) jar McCormick Salad Supreme seasoning', '1 large jar spaghetti sauce, divided', '1 lb. lean ground beef', '1 onion, chopped', '2 (16 oz.) cans kidney beans with sauce', '1 (16 oz.) jar salsa (mild)', '1 Tbsp. chili powder', '1 1/2 lb. top round steak, sliced thin', '4 oz. sliced mushrooms (fresh or canned)', '2 Tbsp. butter or margarine', '1 pkg. Lipton dry onion soup mix', '1 Tbsp. soy sauce', '2 Tbsp. flour', '1 c. milk', '1 c. water', '1 1/2 c. green peppers, sliced thin', '2 pork cutlets or boned pork chops', 'cooking oil', 'Accent', 'garlic powder', 'black pepper', '1/2 c. green pepper, in strips', '1/2 c. onion, diced', '1/2 c. celery, sliced', '1 c. stewed tomatoes', '1 c. tomato sauce', '1 Tbsp. basil', '1 (2 lb.) pkg. sauerkraut', '2 lb. spareribs', '2 apples', '1 pkg. onion soup mix', '1 Tbsp. caraway seed', 'salt', 'pepper', 'sugar', "3 to 4 lb. brisket or top round (If you're not sure, ask the butcher or clerk in the supermarket for a pot roast.)", '1 bottle Heinz chili sauce', '1 pkg. onion soup mix (Knorr or Lipton)', '1 can or bottle beer', '1 qt. sauerkraut, drained', '8 oz. noodles, cooked according to pkg. instructions', '2 cans condensed cream of chicken soup', '1 tsp. dry mustard', '1/2 c. mayonnaise', '1/2 c. chopped onions', '16 oz. corned beef (canned is good)', '8 oz. Swiss cheese, grated', '1/2 c. rye bread crumbs*', '2 cans water', '1 lb. super lean ground beef or ground veal', '1 Tbsp. olive oil', '1 (48 oz.) jar Ragu spaghetti sauce with meat', '1 (8 oz.) can tomato sauce', '1 lb. rigatoni, cooked and drained', '1 Tbsp. oregano', '1 tsp. salt', '1 tsp. garlic powder', '1 tsp. onion powder', '1/4 tsp. black pepper', '12 oz. small curd cottage cheese', '1 lb. Mozzarella cheese, sliced', '2 oz. Parmesan cheese', '4 chicken breast halves', '1 egg', '2 Tbsp. milk', 'salt', 'pepper', 'garlic powder', 'corn flakes', '3 oz. potato pancake mix', '2 eggs', '1 c. water', '1 (15 to 16 oz.) can salmon', '1 green onion, cut into small pieces', '1 Tbsp. parsley', '1 tsp. garlic powder', '1/2 tsp. pepper', 'cooking oil', '1 lb. scallops (fresh are best)', '2 Tbsp. butter', '1 tsp. lemon juice', '1 c. Italian seasoned bread crumbs', '1 c. grated American cheese', '1/2 lb. spinach linguini or fettucini', '1/4 c. butter', '1 tsp. garlic', '1/8 tsp. freshly ground black pepper', '1 c. half and half', '1/2 lb. Sea Stix (salad style)', '1/2 c. Parmesan cheese', '1/2 lb. shrimp', '1/2 lb. scallops', '1/2 lb. crab meat or Sea Stix', '1/2 lb. mushrooms, sliced', '1/4 lb. butter', '1/2 pt. heavy cream', '2 Tbsp. sherry', '1 c. sharp Cheddar cheese', '1 tsp. Worcestershire sauce', '1 tsp. garlic powder', '2 Tbsp. flour', '2 Tbsp. bread crumbs', '12 frozen pastry shells', '1 lb. boneless, skinless chicken breasts', '2 egg yolks', '1 c. ice water', '1 c. flour', '2 Tbsp. sesame oil', '1 Tbsp. soy sauce', '2 Tbsp. honey', '2 Tbsp. sweet and sour sauce', '1 Tbsp. sesame seed', '3/4 lb. shrimp', '2 Tbsp. butter', '1 tsp. garlic powder*', '2 Tbsp. seasoned bread crumbs', 'oregano', '8 oz. spaghetti', '2 Tbsp. butter', '1/2 c. grated Parmesan cheese', '2 eggs, well beaten', '12 oz. cottage cheese', '1 1/4 to 1 1/2 lb. meat loaf mix (beef, veal and pork)', '1/2 c. onion, chopped', '1/2 c. green pepper, chopped', '1 (8 oz.) can sliced tomatoes', '1 (8 oz.) can tomato sauce', '1 tsp. oregano', '1/2 tsp. garlic powder', '1/2 c. shredded Mozzarella cheese', '12 lasagna noodles', '2 Tbsp. olive oil', '2 lb. ground beef', '1/2 c. onion, minced', '2 (6 oz.) cans tomato paste', '1 (15 oz.) can tomato sauce', '2 tsp. basil', '2 tsp. parsley', '2 tsp. sugar', '1 tsp. salt', '1 tsp. oregano', '1/2 tsp. garlic salt', '1/4 tsp. pepper', '16 oz. Ricotta', '8 oz. Mozzarella, sliced', '1 tsp. salt', '1/2 tsp. pepper', '1 lb. boneless pork', '1/2 c. soy sauce', '1 tsp. ginger', '16 oz. Japanese style vegetables or 2 pkg. stir-fry Japanese style vegetables', 'chow mein noodles', '6 green peppers', '1 1/2 lb. meat loaf mix (beef, veal and pork)', '4 eggs', '3/4 c. instant rice', '3/4 c. grated cheese', '1 1/2 tsp. black pepper', '1 1/2 tsp. garlic powder', '1 1/2 tsp. oregano', '1 large jar spaghetti sauce', '1 lb. jumbo shells', '1 1/2 lb. ground beef', '1 medium onion, chopped', '1 egg', '1/2 c. seasoned bread crumbs', '1/4 c. grated Parmesan cheese', '1 tsp. salt', '1/2 tsp. pepper', '16 oz. spaghetti sauce', '3 large zucchini', '2 Tbsp. olive oil', '1 1/4 to 1 1/2 lb. meat loaf mix (beef, pork and veal)', '1 large onion', '1 Tbsp. oregano', '1 tsp. garlic powder', '1 (6 oz.) pkg. chicken flavored rice pilaf mix', '1 (32 oz.) jar spaghetti sauce, divided', '1 c. grated Parmesan cheese', '4 Tbsp. cooking oil', '1 Tbsp. garlic powder', '1 1/4 to 1 1/2 lb. boneless pork, cut into 1-inch cubes', '1 medium onion, chopped', '1 green pepper, cut into 1-inch pieces', '1/2 red pepper (sweet), cut into 1-inch pieces', '1 (15 oz.) can pineapple chunks in natural syrup', '1/4 c. honey', '1/4 c. soy sauce', '2 Tbsp. cider vinegar', '2 to 3 Tbsp. cornstarch', 'chow mein noodles', '1/2 lb. wide noodles', '1 (12 oz.) can Cheddar cheese soup', '6 oz. milk', '1 (5 oz.) can evaporated milk', '2 Tbsp. butter', '2 (6 oz.) cans solid white tuna', '1/2 sweet red pepper, cut up into small pieces', '1 (8 oz.) can sweet peas, drained', '1 Tbsp. Dijon mustard', '1/2 tsp. black pepper', '1 (3 oz.) can French fried onions', '2 medium onions', '1/4 c. butter', '2 (6 1/2 oz.) cans tuna, drained', '2 c. shredded Cheddar, divided', '1 c. baking mix', '1 1/4 c. milk', '1 tsp. seafood seasoning', '3 eggs', '2 medium tomatoes, thinly sliced', '1 (8 oz.) pkg. frozen green peas in cream sauce', '1 c. milk', '2 c. turkey, cubed', '1 1/2 c. mushrooms, sliced', '1 Tbsp. butter', '1 Tbsp. grated Parmesan cheese', '1/2 tsp. garlic powder', '1/2 tsp. black pepper', '1 pkg. Betty Crocker fettuccine Alfredo Tuna Helper', '1 c. cooked turkey or chicken, cut into bite size pieces', '2 lb. veal boneless shoulder, cubed', '2 Tbsp. olive oil', '2 large green peppers, cut into strips', '1 large red pepper, cut into strips', '4 green onions, cut into small pieces', '1/2 lb. mushrooms, sliced', '1 (32 oz.) jar spaghetti sauce', '2 Tbsp. grated Parmesan cheese', '1 tsp. oregano', '3 large zucchini', '4 Tbsp. olive oil, divided', '1 (32 oz.) jar spaghetti sauce, divided', '1 1/2 lb. meat loaf mix (beef, pork and veal)', '1/2 c. chopped onion', '1 Tbsp. oregano', '1 tsp. garlic powder', '6 oz. chicken flavored rice pilaf mix', '1/4 lb. sliced Mozzarella cheese', '1 c. grated Parmesan cheese', '2 lb. fresh asparagus spears or canned asparagus', '1 (10 oz.) can cream of asparagus soup', '1/2 c. sour cream', '1 can French fried onions', '1 lb. frozen cauliflower', '2 (1 lb.) cans asparagus pieces', '1 medium onion, diced fine', '1 can condensed mushroom soup', '4 oz. grated Cheddar cheese', '2 oz. slivered almonds', '1 head broccoli*', '1 c. water', '1/2 tsp. salt', '1 (10 oz.) can broccoli cheese soup', '2 Tbsp. water', '4 oz. sour cream', '1/2 can French fried onions', '1 lb. frozen carrots, sliced', '1/4 lb. butter (1 stick)', '1 (8 oz.) can tomato sauce', '1/4 c. sugar', '1 green onion, diced', '1/4 green pepper, diced', '1 stalk celery, sliced', '1 lb. frozen cauliflower florets', '3 Tbsp. butter', '2 Tbsp. seasoned bread crumbs', '1 Tbsp. sherry', '2 Tbsp. grated cheese', '1 lb. frozen cauliflower florets', '1 can cream of mushroom soup', '4 oz. sour cream', '1/2 c. milk', '1/4 tsp. black pepper', '1/4 tsp. garlic powder', '2 Tbsp. grated Parmesan cheese', '1 (2.8 oz.) can French fried onions, divided', '1 lb. fresh asparagus', '1 Tbsp. sesame seed', '2 Tbsp. butter', '1 tsp. sesame oil', '1 tsp. soy sauce', '4 slices bacon', '2 green onions', '1 (10 oz.) pkg. frozen carrots and peas', '1/2 c. water', '1 1/2 c. shredded lettuce', '1 Tbsp. parsley flakes', '1 tsp. seasoned salt', '1 tsp. garlic powder', '1/2 tsp. pepper', '1/4 c. butter', '1/2 c. onions, chopped', '4 c. cabbage, sliced', '1/2 tsp. salt', '1/4 tsp. pepper', '2 chicken bouillon cubes, crushed']),
        list(['Paula and I collaborated on this recipe, and it was fun.', 'This dish is quite different from my usual fare, but my wonderful wife said it is popular in mill towns.', "I'll list it under vegetables, but it could be used as a main dish.", 'Try it, I think you will be quite pleased.']),
        'www.cookbooks.com/Recipe-Details.aspx?id=301776', 'Gathered',
        array(['american cheese', 'sugar', 'noodles', 'accent', 'chili powder',
               'potato pancake mix', 'green onion', 'sweet and', 'baking mix',
               'sweet red pepper', 'almonds', 'sweet peas', 'cabbage', 'rigatoni',
               'frozen carrots', 'garlic salt', 'water', 'walnuts', 'ground beef',
               'mustard', 'fettucini', 'sour cream', 'wide noodles',
               'ditalini macaroni', 'cream of mushroom soup', 'lasagna noodles',
               'red pepper', 'ground chuck', 'onions', 'eggplant', 'milk',
               'apples', 'sherry', 'cottage cheese', 'beef', 'carrots',
               'fresh asparagus spears', 'jumbo shells', 'onion soup', 'salmon',
               'parsley flakes', 'pork cutlets', 'pepper sauce',
               'salad supreme seasoning', 'shrimp', 'garlic',
               'freshly ground black pepper', 'pastry shells', 'meat',
               'soy sauce', 'mein noodles', 'chicken gravy', 'tuna',
               'italian style bread crumbs', 'swiss cheese', 'turkey',
               'bread crumbs', 'pineapple', 'chopped meat', 'potatoes',
               'kidney beans', 'sweet italian sausage', 'steak sauce',
               'shredded lettuce', 'tomato soup', 'basil', 'garlic powder',
               'super lean ground beef', 'cheddar', 'chicken bouillon cubes',
               'chicken', 'green pepper', 'honey', 'ground lamb', 'spaghetti',
               'ground ham', 'oregano', 'corn', 'cooking oil', 'solid white tuna',
               'japanese style vegetables', 'corned beef', 'grated cheese',
               'spaghetti sauce', 'frozen cauliflower', 'cheddar cheese soup',
               'worcestershire sauce', 'stuffing mix', 'mix', 'scallops',
               'broccoli cheese soup', 'eggs', 'mozzarella cheese', 'rye bread',
               'salad style', 'cornstarch', 'broccoli', 'butter',
               'cream of asparagus soup', 'chicken breasts', 'tomato paste',
               'mozzarella', 'ginger', 'celery', 'sausage', 'helper',
               'lemon juice', 'cheddar cheese', 'onion powder', 'onion',
               'chicken soup', 'crab meat', 'flour', 'chicken broth', 'paprika',
               'onion soup mix', 'salt', 'black pepper', 'heavy cream', 'brisket',
               'spareribs', 'frozen green peas', 'corn bread',
               'hot buttered noodles', 'instant rice', 'dry mustard', 'ham steak',
               'boneless veal', 'sesame seed', 'egg', 'condensed cream',
               'tomatoes', 'bulk sweet sausage', 'garbanzo beans', 'corn flakes',
               'fresh asparagus', 'head cabbage', 'cheese', 'cider vinegar',
               'ham end', 'tomato sauce', 'zucchini', 'mushroom stems',
               'chili sauce', 'parmesan cheese', 'mushrooms', 'salsa',
               'sesame oil', 'sauerkraut', 'green onions',
               'chicken flavored rice pilaf mix', 'thin', 'ricotta', 'ketchup',
               'egg yolks', 'olive oil', 'bacon', 'pepper', 'green peppers',
               'caraway seed', 'seafood seasoning', 'lean ground beef',
               'mayonnaise', 'parsley', 'italian seasoned bread crumbs',
               'condensed mushroom soup', 'boneless pork'], dtype='<U31')         ,
        'www.cookbooks.com', 4, 407]], dtype=object)


df.head(1).values

array([['No-Bake Nut Cookies',
        list(['1 c. firmly packed brown sugar', '1/2 c. evaporated milk', '1/2 tsp. vanilla', '1/2 c. broken nuts (pecans)', '2 Tbsp. butter or margarine', '3 1/2 c. bite size shredded rice biscuits']),
        list(['In a heavy 2-quart saucepan, mix brown sugar, nuts, evaporated milk and butter or margarine.', 'Stir over medium heat until mixture bubbles all over top.', 'Boil and stir 5 minutes more. Take off heat.', 'Stir in vanilla and cereal; mix well.', 'Using 2 teaspoons, drop and shape into 30 clusters on wax paper.', 'Let stand until firm, about 30 minutes.']),
        'www.cookbooks.com/Recipe-Details.aspx?id=44874', 'Gathered',
        array(['bite size shredded rice biscuits', 'vanilla', 'brown sugar',
               'nuts', 'milk', 'butter'], dtype='<U32')                     ,
        'www.cookbooks.com', 6, 6]], dtype=object)


plt.figure(figsize=(16, 6))
sns.boxplot(x=df['No_of_Steps_to_make_recipe'])
plt.show()


df['No_of_Steps_to_make_recipe'].min(), df['No_of_Steps_to_make_recipe'].mean(), df['No_of_Steps_to_make_recipe'].max()

(1, 6.61362790893632, 164)


def labeled_barplot(data, feature, perc=False, n=None, title=None):
    """
    Barplot with percentage at the top

    data: dataframe
    feature: dataframe column
    perc: whether to display percentages instead of count (default is False)
    n: displays the top n category levels (default is None, i.e., display all levels)
    """

    total = len(data[feature])  # length of the column
    count = data[feature].nunique()
    if n is None:
        plt.figure(figsize=(count + 2, 6))
    else:
        plt.figure(figsize=(n + 2, 6))

    plt.xticks(rotation=90, fontsize=15)
    ax = sns.countplot(
        data=data,
        x=feature,
        palette="Paired",
        order=data[feature].value_counts().index[:n],
    )

    for p in ax.patches:
        if perc == True:
            label = "{:.1f}%".format(
                100 * p.get_height() / total
            )  # percentage of each class of the category
        else:
            label = p.get_height()  # count of each level of the category

        x = p.get_x() + p.get_width() / 2  # width of the plot
        y = p.get_height()  # height of the plot

        ax.annotate(
            label,
            (x, y),
            ha="center",
            va="center",
            size=12,
            xytext=(0, 5),
            textcoords="offset points",
        )  # annotate the percentage
    
    plt.title(title)
    plt.show()  # show the plot


labeled_barplot(df, "title", perc=True, n=20, title="Top 20 Recipes")


df[df['title'] == "Chicken Casserole"]


labeled_barplot(df, "source", perc=True, n=2, title="source")


labeled_barplot(df, "site", perc=True, n=20, title="Top 20 site")


labeled_barplot(df, "No_of_Steps_to_make_recipe", perc=True, n=20, title="Top 20 No_of_Steps_to_make_recipe")


labeled_barplot(df, "No_of_ingredients_in_recipe", perc=True, n=20, title="Top 20 No_of_ingredients_in_recipe")


ner = df.ingredients.explode().reset_index()


labeled_barplot(ner, "ingredients", perc=True, n=20, title="Top 20 ingredients")


ingredients = df.ingredients.explode().unique()
ingredients

array(['1 c. firmly packed brown sugar', '1/2 c. evaporated milk',
       '1/2 tsp. vanilla', ..., '1/2 cup very cold seltzer water',
       '1 cup neutral oil, like canola',
       '1/2 cup freshly grated Pecorino Romano cheese, plus more for sprinkling'],
      dtype=object)


print(f"Total Unique Ingredients are {len(ingredients)}")

Total Unique Ingredients are 4682802


stopwords = ['dtype', 'array', 'of', 'the', 'in', 'with', 'or', 'whole', 'all', 'a', 'that', 'using', 'at',
            'and','for','to','until','is', 'then', 'on',"'","U22'","U13'","U32'","U27'","U37'"]

def minimal_wordcloud(df, column):
    text = str(df[column].values)
    wordcloud = WordCloud(width=1000, height=500, stopwords = stopwords).generate(text)
    image = wordcloud.to_image()
    return image


minimal_wordcloud(df, 'title')


minimal_wordcloud(df, 'ingredients')


minimal_wordcloud(df, 'directions')


minimal_wordcloud(df, 'NER')


ingredient_uses = df[["title", "NER"]].explode("NER")
ingredient_uses = ingredient_uses.rename(columns={"NER": "ingredient"})
ingredient_uses


all_ingredients = ingredient_uses.ingredient.value_counts().head(20).index.tolist()
for i in all_ingredients:
    # Find id's of recipes using the ingredient
    id_list = ingredient_uses[ingredient_uses.ingredient == i].index.unique()
    # Find all rows for the above id's and do value_counts on those rows
    print(i, "with", ingredient_uses[ingredient_uses.index.isin(id_list)].ingredient.value_counts().head(10).index.tolist()[1:])
    print()

salt with ['flour', 'sugar', 'butter', 'eggs', 'onion', 'garlic', 'milk', 'water', 'pepper']

sugar with ['salt', 'flour', 'eggs', 'vanilla', 'butter', 'milk', 'water', 'baking powder', 'baking soda']

butter with ['salt', 'flour', 'sugar', 'eggs', 'milk', 'vanilla', 'brown sugar', 'onion', 'baking powder']

flour with ['salt', 'sugar', 'eggs', 'butter', 'vanilla', 'milk', 'baking powder', 'baking soda', 'egg']

eggs with ['salt', 'sugar', 'flour', 'butter', 'vanilla', 'milk', 'baking powder', 'baking soda', 'brown sugar']

onion with ['salt', 'garlic', 'pepper', 'water', 'butter', 'tomatoes', 'celery', 'olive oil', 'milk']

garlic with ['salt', 'onion', 'olive oil', 'tomatoes', 'water', 'butter', 'pepper', 'parsley', 'oregano']

milk with ['salt', 'sugar', 'flour', 'butter', 'eggs', 'vanilla', 'baking powder', 'onion', 'egg']

water with ['salt', 'sugar', 'flour', 'onion', 'butter', 'garlic', 'eggs', 'milk', 'pepper']

vanilla with ['sugar', 'flour', 'eggs', 'salt', 'butter', 'milk', 'baking powder', 'baking soda', 'brown sugar']

olive oil with ['salt', 'garlic', 'onion', 'tomatoes', 'water', 'pepper', 'parsley', 'butter', 'lemon juice']

pepper with ['salt', 'onion', 'garlic', 'butter', 'milk', 'water', 'olive oil', 'flour', 'tomatoes']

brown sugar with ['salt', 'flour', 'butter', 'vanilla', 'eggs', 'sugar', 'baking soda', 'cinnamon', 'baking powder']

egg with ['salt', 'flour', 'sugar', 'butter', 'milk', 'vanilla', 'baking powder', 'baking soda', 'brown sugar']

tomatoes with ['salt', 'garlic', 'onion', 'olive oil', 'water', 'pepper', 'onions', 'oregano', 'parsley']

baking powder with ['flour', 'salt', 'sugar', 'eggs', 'vanilla', 'butter', 'milk', 'baking soda', 'egg']

lemon juice with ['salt', 'sugar', 'garlic', 'butter', 'olive oil', 'water', 'flour', 'onion', 'eggs']

cinnamon with ['sugar', 'salt', 'flour', 'eggs', 'butter', 'vanilla', 'brown sugar', 'nutmeg', 'baking soda']

sour cream with ['salt', 'butter', 'onion', 'sugar', 'eggs', 'flour', 'cheddar cheese', 'cream cheese', 'garlic']

baking soda with ['flour', 'salt', 'sugar', 'eggs', 'vanilla', 'butter', 'baking powder', 'brown sugar', 'egg']


all_ingredients = ingredient_uses.ingredient.value_counts().head(20).index.tolist()


network_data = []

for i in all_ingredients:
    
    # Find id's of recipes using the ingredient
    id_list = ingredient_uses[ingredient_uses.ingredient == i].index.unique()
    
    # Find all rows for the above id's and do value_counts on those rows
    for j in ingredient_uses[ingredient_uses.index.isin(id_list)].ingredient.value_counts().head(10).index.tolist()[1:]:
        i = " ".join(re.findall(r'[a-zA-Z]+', i))
        j = " ".join(re.findall(r'[a-zA-Z]+', j))
        network_data.append([i, j])


network_data = pd.DataFrame(data=network_data, columns=['Ingredient', 'Related Ingredients'])

network_data.head()


network_data = network_data.drop_duplicates()
network_data = network_data[network_data["Ingredient"] != network_data["Related Ingredients"]]


def plot_network(dataframe, ingredient_name=None):
    # Create a directed graph
    G = nx.DiGraph()
    
    if ingredient_name is not None:
        dataframe = dataframe[dataframe['Ingredient']==ingredient_name]
    else:
        ingredient_name = ""
        
    # Add nodes and edges from the dataframe
    for index, row in dataframe.iterrows():
        ingredient = row['Ingredient']
        related_ingredients = row['Related Ingredients']
        G.add_node(ingredient, label=ingredient)  # Add 'label' attribute to store the node name
        G.add_node(related_ingredients, label=related_ingredients)  # Add 'label' attribute to store the node name
        G.add_edge(ingredient, related_ingredients)

    # Plot the network
    plt.figure(figsize=(20, 13))
    pos = nx.spring_layout(G, seed=42)
    node_labels = nx.get_node_attributes(G, 'label')
    nx.draw_networkx(G, pos, with_labels=True, node_size=5000, node_color='lightblue', edge_color='gray', font_size=12, labels=node_labels)  # Use 'labels' argument to display node names
    plt.title("Related Ingredients of "+ingredient_name)
    
    # Show the plot
    plt.axis('off')
    plt.show()

plot_network(network_data)


plot_network(network_data, "soda")


tf = TfidfVectorizer(analyzer='word',ngram_range=(1, 2),min_df=0, stop_words='english')
tfidf_matrix = tf.fit_transform(df["NER"].astype(str)[1:-1][:10000])


cosine_sim = linear_kernel(tfidf_matrix, tfidf_matrix)


df_small = df.reset_index()[:10000]
titles = df_small['title']
indices = pd.Series(df_small.index, index=df_small['title'])


df_small['title'].values

array(['No-Bake Nut Cookies', "Jewell Ball'S Chicken", 'Creamy Corn', ...,
       'Chicken Casserole', 'Sweet Potatoes Casserole', '7 Layer Salad'],
      dtype=object)


def get_recommendations(title, no_of_recipes):
    idx = indices[title]
    sim_scores = list(enumerate(cosine_sim[idx]))
    sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True)
    sim_scores = sim_scores[1:31]
    recipe_indices = [i[0] for i in sim_scores]
    return titles.iloc[recipe_indices].head(no_of_recipes)


recommended_recipes = get_recommendations("Sweet Potatoes Casserole", 10)
recommended_recipes

5359       The "Bestest" Banana Bread
7703                    Custard Sauce
623             Baked Pork Tenderloin
3164    Broccoli And Cheese Casserole
3842                 Strawberry Pizza
1952                    Pumpkin Bread
5075            Crustless Egg Custard
2005           Cathedral Window Candy
2385                    Quick Dessert
5969                  Chicken Lasagna
Name: title, dtype: object


recommended_recipes = get_recommendations("Creamy Corn", 5)
recommended_recipes

8100               Peanut Butter Pie
3695    Baked Halibut, Italian Style
9641           Chinese Chicken Wings
446            Sour Cream Pound Cake
9470              Broccoli Casserole
Name: title, dtype: object


# Recipe data
recipe_data = df.head(1000)

def find_best_recipe(ingredients):
    best_recipe = None
    best_match_count = 0

    for _, recipe in recipe_data.iterrows():
        recipe_ingredients = recipe['ingredients']
        match_count = sum(1 for ingredient in ingredients if ingredient in recipe_ingredients)

        if match_count > best_match_count:
            best_recipe = recipe
            best_match_count = match_count

    return best_recipe

def print_recipe_directions(recipe, ingredients):
    directions = recipe['directions']
    
    print("You have ingredients:\n")
    print("\n".join(ingredients))
    print("\n")
    print("If you arrange following ingredient(s) then you can make Recipe:\n")
    
    extra = set(recipe['ingredients']).difference(set(ingredients))
    print("\n".join(extra))
    print("\n")
    
    print("Recipe Directions:\n")
    print("\n".join(directions))


# List of ingredients
input_ingredients = ['1 c. firmly packed brown sugar', '1/2 c. evaporated milk', '1/2 tsp. vanilla']

# Find the best recipe
best_recipe = find_best_recipe(input_ingredients)

# Print the best recipe directions
if best_recipe is not None:
    print_recipe_directions(best_recipe, input_ingredients)
else:
    print("No matching recipe found.")

You have ingredients:

1 c. firmly packed brown sugar
1/2 c. evaporated milk
1/2 tsp. vanilla


If you arrange following ingredient(s) then you can make Recipe:

1/2 c. broken nuts (pecans)
3 1/2 c. bite size shredded rice biscuits
2 Tbsp. butter or margarine


Recipe Directions:

In a heavy 2-quart saucepan, mix brown sugar, nuts, evaporated milk and butter or margarine.
Stir over medium heat until mixture bubbles all over top.
Boil and stir 5 minutes more. Take off heat.
Stir in vanilla and cereal; mix well.
Using 2 teaspoons, drop and shape into 30 clusters on wax paper.
Let stand until firm, about 30 minutes.


# List of ingredients
input_ingredients = ['1 box powdered sugar', '8 oz. soft butter', '1 (8 oz.) peanut butter', 'paraffin']

# Find the best recipe
best_recipe = find_best_recipe(input_ingredients)

# Print the best recipe directions
if best_recipe is not None:
    print_recipe_directions(best_recipe, input_ingredients)
else:
    print("No matching recipe found.")

You have ingredients:

1 box powdered sugar
8 oz. soft butter
1 (8 oz.) peanut butter
paraffin


If you arrange following ingredients then you can make Recipe:

12 oz. chocolate chips


Recipe Directions:

Mix sugar, butter and peanut butter.
Roll into balls and place on cookie sheet.
Set in freezer for at least 30 minutes. Melt chocolate chips and paraffin in double boiler.
Using a toothpick, dip balls 3/4 of way into chocolate chip and paraffin mixture to make them look like buckeyes.


# Preprocess the recipe directions
directions = df['directions'].head(1000).values.tolist()

# Text preprocessing
tokenizer = Tokenizer()
tokenizer.fit_on_texts(directions)
total_words = len(tokenizer.word_index) + 1

input_sequences = []
for line in directions:
    token_list = tokenizer.texts_to_sequences([line])[0]
    for i in range(1, len(token_list)):
        n_gram_sequence = token_list[:i+1]
        input_sequences.append(n_gram_sequence)

# Pad sequences for input to the model
max_sequence_len = max([len(seq) for seq in input_sequences])
input_sequences = pad_sequences(input_sequences, maxlen=max_sequence_len, padding='pre')

# Create predictors and label
predictors, label = input_sequences[:, :-1], input_sequences[:, -1]

# Convert label to one-hot encoding
label = tensorflow.keras.utils.to_categorical(label, num_classes=total_words)

# Build the model
model = Sequential()
model.add(Embedding(total_words, 100, input_length=max_sequence_len-1))
model.add(LSTM(150))
model.add(Dense(total_words, activation='softmax'))

model.compile(loss='categorical_crossentropy', optimizer='adam')

# Train the model
model.fit(predictors, label, epochs=100, verbose=2)

Epoch 1/100
128/128 - 10s - loss: 8.4358 - 10s/epoch - 82ms/step
Epoch 2/100
128/128 - 7s - loss: 8.4406 - 7s/epoch - 52ms/step
Epoch 3/100
128/128 - 7s - loss: 8.3241 - 7s/epoch - 52ms/step
Epoch 4/100
128/128 - 7s - loss: 8.1545 - 7s/epoch - 51ms/step
Epoch 5/100
128/128 - 7s - loss: 7.8082 - 7s/epoch - 52ms/step
Epoch 6/100
128/128 - 7s - loss: 7.3336 - 7s/epoch - 52ms/step
Epoch 7/100
128/128 - 7s - loss: 6.7790 - 7s/epoch - 51ms/step
Epoch 8/100
128/128 - 7s - loss: 6.1823 - 7s/epoch - 52ms/step
Epoch 9/100
128/128 - 7s - loss: 5.5900 - 7s/epoch - 52ms/step
Epoch 10/100
128/128 - 7s - loss: 5.0163 - 7s/epoch - 51ms/step
Epoch 11/100
128/128 - 7s - loss: 4.4567 - 7s/epoch - 52ms/step
Epoch 12/100
128/128 - 7s - loss: 3.9323 - 7s/epoch - 52ms/step
Epoch 13/100
128/128 - 7s - loss: 3.4422 - 7s/epoch - 51ms/step
Epoch 14/100
128/128 - 7s - loss: 2.9918 - 7s/epoch - 52ms/step
Epoch 15/100
128/128 - 7s - loss: 2.5750 - 7s/epoch - 52ms/step
Epoch 16/100
128/128 - 7s - loss: 2.1964 - 7s/epoch - 52ms/step
Epoch 17/100
128/128 - 7s - loss: 1.8682 - 7s/epoch - 52ms/step
Epoch 18/100
128/128 - 7s - loss: 1.5784 - 7s/epoch - 52ms/step
Epoch 19/100
128/128 - 7s - loss: 1.3308 - 7s/epoch - 51ms/step
Epoch 20/100
128/128 - 7s - loss: 1.1199 - 7s/epoch - 52ms/step
Epoch 21/100
128/128 - 7s - loss: 0.9449 - 7s/epoch - 51ms/step
Epoch 22/100
128/128 - 7s - loss: 0.7964 - 7s/epoch - 52ms/step
Epoch 23/100
128/128 - 7s - loss: 0.6743 - 7s/epoch - 51ms/step
Epoch 24/100
128/128 - 7s - loss: 0.5716 - 7s/epoch - 51ms/step
Epoch 25/100
128/128 - 7s - loss: 0.4872 - 7s/epoch - 52ms/step
Epoch 26/100
128/128 - 7s - loss: 0.4164 - 7s/epoch - 52ms/step
Epoch 27/100
128/128 - 7s - loss: 0.3584 - 7s/epoch - 53ms/step
Epoch 28/100
128/128 - 7s - loss: 0.3133 - 7s/epoch - 51ms/step
Epoch 29/100
128/128 - 7s - loss: 0.2754 - 7s/epoch - 52ms/step
Epoch 30/100
128/128 - 7s - loss: 0.2451 - 7s/epoch - 51ms/step
Epoch 31/100
128/128 - 7s - loss: 0.2176 - 7s/epoch - 52ms/step
Epoch 32/100
128/128 - 7s - loss: 0.1961 - 7s/epoch - 52ms/step
Epoch 33/100
128/128 - 7s - loss: 0.1791 - 7s/epoch - 52ms/step
Epoch 34/100
128/128 - 7s - loss: 0.1647 - 7s/epoch - 52ms/step
Epoch 35/100
128/128 - 7s - loss: 0.1518 - 7s/epoch - 52ms/step
Epoch 36/100
128/128 - 7s - loss: 0.1405 - 7s/epoch - 52ms/step
Epoch 37/100
128/128 - 7s - loss: 0.1311 - 7s/epoch - 51ms/step
Epoch 38/100
128/128 - 7s - loss: 0.1236 - 7s/epoch - 52ms/step
Epoch 39/100
128/128 - 7s - loss: 0.1162 - 7s/epoch - 52ms/step
Epoch 40/100
128/128 - 7s - loss: 0.1099 - 7s/epoch - 52ms/step
Epoch 41/100
128/128 - 7s - loss: 0.1048 - 7s/epoch - 52ms/step
Epoch 42/100
128/128 - 7s - loss: 0.0988 - 7s/epoch - 52ms/step
Epoch 43/100
128/128 - 7s - loss: 0.0960 - 7s/epoch - 52ms/step
Epoch 44/100
128/128 - 7s - loss: 0.0917 - 7s/epoch - 52ms/step
Epoch 45/100
128/128 - 7s - loss: 0.0877 - 7s/epoch - 52ms/step
Epoch 46/100
128/128 - 7s - loss: 0.0846 - 7s/epoch - 52ms/step
Epoch 47/100
128/128 - 7s - loss: 0.0815 - 7s/epoch - 52ms/step
Epoch 48/100
128/128 - 7s - loss: 0.0786 - 7s/epoch - 51ms/step
Epoch 49/100
128/128 - 7s - loss: 0.0765 - 7s/epoch - 52ms/step
Epoch 50/100
128/128 - 7s - loss: 0.0754 - 7s/epoch - 52ms/step
Epoch 51/100
128/128 - 7s - loss: 0.0728 - 7s/epoch - 51ms/step
Epoch 52/100
128/128 - 7s - loss: 0.0710 - 7s/epoch - 52ms/step
Epoch 53/100
128/128 - 7s - loss: 0.0691 - 7s/epoch - 52ms/step
Epoch 54/100
128/128 - 7s - loss: 0.0687 - 7s/epoch - 51ms/step
Epoch 55/100
128/128 - 7s - loss: 0.0669 - 7s/epoch - 52ms/step
Epoch 56/100
128/128 - 7s - loss: 0.0649 - 7s/epoch - 52ms/step
Epoch 57/100
128/128 - 7s - loss: 0.0634 - 7s/epoch - 52ms/step
Epoch 58/100
128/128 - 7s - loss: 0.0625 - 7s/epoch - 52ms/step
Epoch 59/100
128/128 - 7s - loss: 0.0618 - 7s/epoch - 52ms/step
Epoch 60/100
128/128 - 7s - loss: 0.0615 - 7s/epoch - 51ms/step
Epoch 61/100
128/128 - 7s - loss: 0.0605 - 7s/epoch - 52ms/step
Epoch 62/100
128/128 - 7s - loss: 0.0587 - 7s/epoch - 52ms/step
Epoch 63/100
128/128 - 7s - loss: 0.0582 - 7s/epoch - 52ms/step
Epoch 64/100
128/128 - 7s - loss: 0.0607 - 7s/epoch - 52ms/step
Epoch 65/100
128/128 - 7s - loss: 0.0587 - 7s/epoch - 52ms/step
Epoch 66/100
128/128 - 7s - loss: 0.0574 - 7s/epoch - 52ms/step
Epoch 67/100
128/128 - 7s - loss: 0.0582 - 7s/epoch - 52ms/step
Epoch 68/100
128/128 - 7s - loss: 0.0599 - 7s/epoch - 52ms/step
Epoch 69/100
128/128 - 7s - loss: 0.0584 - 7s/epoch - 52ms/step
Epoch 70/100
128/128 - 7s - loss: 0.0563 - 7s/epoch - 52ms/step
Epoch 71/100
128/128 - 7s - loss: 0.0552 - 7s/epoch - 52ms/step
Epoch 72/100
128/128 - 7s - loss: 0.0537 - 7s/epoch - 52ms/step
Epoch 73/100
128/128 - 7s - loss: 0.0538 - 7s/epoch - 51ms/step
Epoch 74/100
128/128 - 7s - loss: 0.0530 - 7s/epoch - 52ms/step
Epoch 75/100
128/128 - 7s - loss: 0.0534 - 7s/epoch - 52ms/step
Epoch 76/100
128/128 - 7s - loss: 0.0526 - 7s/epoch - 52ms/step
Epoch 77/100
128/128 - 7s - loss: 0.0521 - 7s/epoch - 52ms/step
Epoch 78/100
128/128 - 7s - loss: 0.0524 - 7s/epoch - 52ms/step
Epoch 79/100
128/128 - 7s - loss: 0.0521 - 7s/epoch - 53ms/step
Epoch 80/100
128/128 - 7s - loss: 0.0512 - 7s/epoch - 55ms/step
Epoch 81/100
128/128 - 7s - loss: 0.0510 - 7s/epoch - 52ms/step
Epoch 82/100
128/128 - 7s - loss: 0.0510 - 7s/epoch - 52ms/step
Epoch 83/100
128/128 - 7s - loss: 0.0506 - 7s/epoch - 52ms/step
Epoch 84/100
128/128 - 7s - loss: 0.0499 - 7s/epoch - 52ms/step
Epoch 85/100
128/128 - 7s - loss: 0.0500 - 7s/epoch - 52ms/step
Epoch 86/100
128/128 - 7s - loss: 0.0506 - 7s/epoch - 52ms/step
Epoch 87/100
128/128 - 7s - loss: 0.0495 - 7s/epoch - 52ms/step
Epoch 88/100
128/128 - 7s - loss: 0.0507 - 7s/epoch - 52ms/step
Epoch 89/100
128/128 - 7s - loss: 0.0531 - 7s/epoch - 52ms/step
Epoch 90/100
128/128 - 7s - loss: 0.0613 - 7s/epoch - 52ms/step
Epoch 91/100
128/128 - 7s - loss: 0.0633 - 7s/epoch - 52ms/step
Epoch 92/100
128/128 - 7s - loss: 0.0573 - 7s/epoch - 52ms/step
Epoch 93/100
128/128 - 7s - loss: 0.0513 - 7s/epoch - 52ms/step
Epoch 94/100
128/128 - 7s - loss: 0.0493 - 7s/epoch - 53ms/step
Epoch 95/100
128/128 - 7s - loss: 0.0488 - 7s/epoch - 52ms/step
Epoch 96/100
128/128 - 7s - loss: 0.0490 - 7s/epoch - 52ms/step
Epoch 97/100
128/128 - 7s - loss: 0.0480 - 7s/epoch - 52ms/step
Epoch 98/100
128/128 - 7s - loss: 0.0482 - 7s/epoch - 52ms/step
Epoch 99/100
128/128 - 7s - loss: 0.0482 - 7s/epoch - 52ms/step
Epoch 100/100
128/128 - 7s - loss: 0.0482 - 7s/epoch - 52ms/step

<keras.src.callbacks.History at 0x238d7322d10>


# Generate new recipe directions
seed_text = "In a large bowl, mix"
next_words = 3

for _ in range(next_words):
    token_list = tokenizer.texts_to_sequences([seed_text])[0]
    token_list = pad_sequences([token_list], maxlen=max_sequence_len, padding='pre')  # Modify maxlen argument
    predicted = model.predict(token_list, verbose=0)  # Replace predict_classes with predict
    
    predicted_word_index = np.argmax(predicted)
    output_word = ""
    for word, index in tokenizer.word_index.items():
        if index == predicted_word_index:
            output_word = word
            break
    seed_text += " " + output_word

# Print the generated recipe directions
print("Generated Directions:", seed_text)

Generated Directions: In a large bowl, mix peel and slice. set aside. put in casserole dish. brush with remaining barbecue sauce. conventional oven:


# Generate new recipe directions
seed_text = "Get 2 tsp sugar and"
next_words = 3

for _ in range(next_words):
    token_list = tokenizer.texts_to_sequences([seed_text])[0]
    token_list = pad_sequences([token_list], maxlen=max_sequence_len, padding='pre')  # Modify maxlen argument
    predicted = model.predict(token_list, verbose=0)  # Replace predict_classes with predict
    
    predicted_word_index = np.argmax(predicted)
    output_word = ""
    for word, index in tokenizer.word_index.items():
        if index == predicted_word_index:
            output_word = word
            break
    seed_text += " " + output_word

# Print the generated recipe directions
print("Generated Directions:", seed_text)

Generated Directions: Get 2 tsp sugar and add water, frozen vegetables, potatoes and celery. turn cake out onto a heavy piece of aluminum foil which has been placed on a cookie sheet. bake in moderate oven until brown.


# Load the recipe dataset
recipe_data = df.head(45)

# Preprocess NER column to extract ingredients

# Text vectorization
vectorizer = TfidfVectorizer()
X = vectorizer.fit_transform(recipe_data['NER'].astype(str))

# Clustering
n_clusters = 3
kmeans = KMeans(n_clusters=n_clusters)
kmeans.fit(X)

# Dimensionality reduction
pca = PCA(n_components=2)
X_pca = pca.fit_transform(X.toarray())

# Plot recipe clusters
colors = ['red', 'green', 'blue']  # Customize cluster colors
markers = ['o', 's', 'D']  # Customize cluster markers

plt.figure(figsize=(8, 6))
for i in range(n_clusters):
    cluster_points = X_pca[kmeans.labels_ == i]
    plt.scatter(cluster_points[:, 0], cluster_points[:, 1], c=colors[i], marker=markers[i], label=f'Cluster {i+1}')

plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')
plt.title('Recipe Clusters')
plt.legend()
plt.show()

# Display recipe clusters
recipe_data['Cluster'] = kmeans.labels_

for cluster_id in range(n_clusters):
    cluster_recipes = recipe_data[recipe_data['Cluster'] == cluster_id]
    print(f"\nCluster {cluster_id+1} Recipes:")
    for _, recipe in cluster_recipes.iterrows():
        print(recipe['title'])

F:\ProgramData\anaconda3\lib\site-packages\sklearn\cluster\_kmeans.py:870: FutureWarning: The default value of `n_init` will change from 10 to 'auto' in 1.4. Set the value of `n_init` explicitly to suppress the warning
  warnings.warn(

Cluster 1 Recipes:
Nolan'S Pepper Steak
Double Cherry Delight
Quick Barbecue Wings
Pink Stuff(Frozen Dessert)  
Fresh Strawberry Pie
Cuddy Farms Marinated Turkey
Spaghetti Sauce To Can
Prize-Winning Meat Loaf
Corral Barbecued Beef Steak Strips
One Hour Rolls
Punch Bowl Fruit Salad
Summer Chicken
Tuna Macaroni Casserole
Artichoke Dip
Summer Spaghetti
Watermelon Rind Pickles
Angel Biscuits
Quick Peppermint Puffs

Cluster 2 Recipes:
No-Bake Nut Cookies
Reeses Cups(Candy)  
Rhubarb Coffee Cake
Millionaire Pie
Buckeye Candy
Easy German Chocolate Cake
Broccoli Salad
Eggless Milkless Applesauce Cake
Grandma Hanrath'S Banana Breadfort Collins, Colorado  
Easy Fudge
Cherry Pizza
Chicken Stew
Quick Coffee Cake(6 Servings)  
Fruit Pizza

Cluster 3 Recipes:
Jewell Ball'S Chicken
Creamy Corn
Chicken Funny
Cheeseburger Potato Soup
Scalloped Corn
Taco Salad Chip Dip
Strawberry Whatever
Chocolate Frango Mints
Smothered Round Steak(Servings: 4)  
Taco-Filled Green Pepper
Potato And Cheese Pie
Broccoli Dip For Crackers
Pear-Lime Salad

C:\Users\Admin\AppData\Local\Temp\ipykernel_11224\1220178402.py:41: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  recipe_data['Cluster'] = kmeans.labels_

	title	ingredients	directions	link	source	NER	site	No_of_Steps_to_make_recipe	No_of_ingredients_in_recipe
1335130	Roasted Garlic & Dill Dressing	[1 bulb of garlic 1cup buttermilk 1/2 cup mayo...	[cut top off garlic, drizzle small amount of o...	www.epicurious.com/recipes/member/views/roaste...	Gathered	[garlic]	www.epicurious.com	1	1
57305	Cottage Cheese	[any amount sour milk or fresh clabber]	[Heat sour milk to a temperature of about 98° ...	www.cookbooks.com/Recipe-Details.aspx?id=651009	Gathered	[sour milk]	www.cookbooks.com	4	1
2223401	Peg's Strawberry Tarts Recipe	[1 quart. strawberries]	[CREAM FILLING: Beat all ingredients together ...	cookeatshare.com/recipes/peg-s-strawberry-tart...	Recipes1M	[strawberries]	cookeatshare.com	6	1
1330070	Brazilian Black Bean Soup	[ingredients]	[Rinse the beans. Cover them with water, and l...	www.epicurious.com/recipes/member/views/brazil...	Gathered	[ingredients]	www.epicurious.com	11	1
1933284	Bubble Gum Ice Tea Recipe	[2 ounce Bubble Gum Schnapps fill ice tea]	[Ice // rocks]	cookeatshare.com/recipes/bubble-gum-ice-tea-94464	Recipes1M	[fill ice tea]	cookeatshare.com	1	1
...	...	...	...	...	...	...	...	...	...
1997023	D.I.Y Spice Blends (No3)	[1/2 cup dry mustard powder, 1/2 cup ground tu...	[Mix the ingredients together well, then trans...	cookpad.com/us/recipes/367445-diy-spice-blends...	Recipes1M	[sugar, brown sugar, anise, ground fennel seed...	cookpad.com	40	99
719917	Dumplings And Cabbage	[1 c. flour, 1 egg, milk, dash of salt, 1/2 c....	[If you do not have large potatoes, use more o...	www.cookbooks.com/Recipe-Details.aspx?id=301825	Gathered	[bread, sugar, brown sugar, fresh mushrooms, r...	www.cookbooks.com	5	223
27310	Strawberry Butter	[1 c. powdered sugar, 1 egg yolk, 1/2 c. butte...	[My daughter made this soup, and I thought it ...	www.cookbooks.com/Recipe-Details.aspx?id=301676	Gathered	[bisquick, bread, sugar, noodles, liquid smoke...	www.cookbooks.com	1	285
122527	Layered Salad	[lettuce, torn into small pieces, carrots, gra...	[This recipe was in the drawer for some years,...	www.cookbooks.com/Recipe-Details.aspx?id=301736	Gathered	[sugar, chunky chicken, curry powder, accent, ...	www.cookbooks.com	5	338
719239	Grandma'S Chicken Fricassee	[1 lb. chopped meat, 1 egg, 1/2 c. seasoned br...	[Paula and I collaborated on this recipe, and ...	www.cookbooks.com/Recipe-Details.aspx?id=301776	Gathered	[american cheese, sugar, noodles, accent, chil...	www.cookbooks.com	4	407

	title	ingredients	directions	link	source	NER	site	No_of_Steps_to_make_recipe	No_of_ingredients_in_recipe
1294279	Broccoli Salad	[2 c. chopped fresh broccoli, 1/2 c. unsalted ...	[Combine first ingredients and fold in with dr...	www.epicurious.com/recipes/member/views/brocco...	Gathered	[fresh broccoli, wine vinegar, dressing, ¼, gr...	www.epicurious.com	1	8
1575108	Cape Cod Cocktail	[4 ounces, fluid Cranberry Juice, 1 ounce, flu...	[Pour the cranberry juice and vodka into a hig...	tastykitchen.com/recipes/drinks/cape-cod-cockt...	Gathered	[lime, fluid vodka, cranberry juice]	tastykitchen.com	1	3
1273781	Grandmother Cora Horton'S Millionaire Fudge	[4 1/2 c. white sugar, 1 tall can evaporated m...	[Chocolate, nuts and marshmallow stuff into a ...	www.epicurious.com/recipes/member/views/grandm...	Gathered	[white sugar, oleo, marshmallow cream, walnuts...	www.epicurious.com	1	6
1575110	Vanilla Cinnamon Smoothie	[1/2 cups Whole Milk, 3/4 cups Plain Greek Yog...	[In a blender, add all ingredients and run on ...	tastykitchen.com/recipes/drinks/vanilla-cinnam...	Gathered	[¼, greek yogurt, cinnamon, milk]	tastykitchen.com	1	4
522016	Meringue Cookies	[2 large egg whites, 3/4 c. sugar, 1 tsp. vani...	[Beat egg whites until foamy. Gradually add su...	www.cookbooks.com/Recipe-Details.aspx?id=14161	Gathered	[sugar, vanilla, egg whites]	www.cookbooks.com	1	3
...	...	...	...	...	...	...	...	...	...
2012938	Making Egg Dough Pastas	[DRY, 2 cups all-purpose flour, WET, 9 egg yol...	[Measure the flour and shake it through a siev...	www.epicurious.com/recipes/food/views/making-e...	Recipes1M	[extra-virgin olive oil, wet, egg yolk, eggs, ...	www.epicurious.com	145	21
1702484	Cannelloni with Asparagus and Ham	[2 pounds asparagus, 6 tablespoons butter, 1 c...	[Trim 1 inch or more off the butt ends of the ...	www.cookstr.com/recipes/cannelloni-with-aspara...	Recipes1M	[nutmeg, eggs, ham, water, flour, asparagus, m...	www.cookstr.com	148	13
2210363	Soft Cheesy Pretzel	[1 1/2 cups flour, all-purpose, 2 teaspoons ba...	[Combine first 4 ingredients in a medium bowl;...	recipeland.com/recipe/v/soft-cheesy-pretzel--5...	Recipes1M	[baking powder, sugar, eggs, cheddar cheese, f...	recipeland.com	151	9
1739457	Mike's NY Cheesecake 101	[30 Graham Crackers (crushed for crust), 4 tbs...	[Preheat oven to 350 (175 degrees C)., Triple ...	cookpad.com/us/recipes/352287-mikes-ny-cheesec...	Recipes1M	[mixing bowl, sugar, vanilla, crackers, eggs, ...	cookpad.com	163	19
1717085	Moon Cakes	[1 1/4 cups sugar, 1/4 plus 1/8 teaspoon citri...	[In a small saucepan, combine the sugar, citri...	www.epicurious.com/recipes/food/views/moon-cak...	Recipes1M	[caramel sauce, pork fatback, sugar, eggs, siu...	www.epicurious.com	164	27

	title	ingredients	directions	link	source	NER	site	No_of_Steps_to_make_recipe	No_of_ingredients_in_recipe
63	Chicken Casserole	[1 can cream of mushroom soup, 1 can cream of ...	[Mix all ingredients together in baking dish.,...	www.cookbooks.com/Recipe-Details.aspx?id=665397	Gathered	[cream of chicken soup, cream of mushroom soup...	www.cookbooks.com	3	6
131	Chicken Casserole	[1/2 c. raw rice, 1 can French onion soup, 1 c...	[Mix all together; pour into a 7 x 12-inch cas...	www.cookbooks.com/Recipe-Details.aspx?id=661800	Gathered	[cream of chicken, onion soup, mushrooms, bite...	www.cookbooks.com	3	5
356	Chicken Casserole	[1 1/2 c. uncooked rice, 1 envelope onion soup...	[Spread rice in bottom of a 9 x 13-inch glass ...	www.cookbooks.com/Recipe-Details.aspx?id=419575	Gathered	[onion soup, cream of mushroom soup, water, ri...	www.cookbooks.com	4	5
428	Chicken Casserole	[1 large pkg. spinach noodles, cooked in broth...	[Cook chicken. Saute celery, pepper and onion....	www.cookbooks.com/Recipe-Details.aspx?id=7283	Gathered	[velveeta cheese, chicken breasts, spinach noo...	www.cookbooks.com	1	8
539	Chicken Casserole	[4 c. cooked chicken, 1 c. chopped celery, 1 c...	[Mix first nine ingredients., Saute 5 minutes ...	www.cookbooks.com/Recipe-Details.aspx?id=115061	Gathered	[cream of chicken soup, slivered almonds, lemo...	www.cookbooks.com	4	12
...	...	...	...	...	...	...	...	...	...
2155999	Chicken Casserole	[1 lb Chicken Breast (cubed), 5 Carrots (slice...	[Preheat oven to 350F, Boil carrots, Cube chic...	cookpad.com/us/recipes/346285-chicken-casserole	Recipes1M	[cream of chicken soup, sour cream, corn, ranc...	cookpad.com	8	12
2169171	Chicken Casserole	[1 (6 ounce) packagestove top chicken flavor s...	[Preheat oven to 350 degrees F., Prepare stuff...	www.food.com/recipe/chicken-casserole-268828	Recipes1M	[velveeta cheese, condensed cream, chicken fla...	www.food.com	6	4
2199641	Chicken Casserole	[2 cups cooked egg noodles, 2 (10 3/4 ounce) c...	[Preheat oven to 350., In a large bowl, toss t...	www.food.com/recipe/chicken-casserole-228128	Recipes1M	[pimiento, cream of mushroom soup, sherry wine...	www.food.com	5	10
2214015	Chicken Casserole	[1 12 loaves artisan bread (example-sourdough ...	[At least 8 hours before you plan to serve thi...	www.food.com/recipe/chicken-casserole-522180	Recipes1M	[bread, chicken breasts, unsalted butter, heav...	www.food.com	25	17
2226534	Chicken Casserole	[1 tablespoon butter, 1 tablespoon olive oil, ...	[Saute leek, onion and garlic in melted butter...	www.food.com/recipe/chicken-casserole-171504	Recipes1M	[corn, ground cumin, chicken breasts, potato, ...	www.food.com	10	18

Load Python Libraries Here¶

Read Dataset¶

What fields are in the data?¶

How do fields in the data relate to each other?¶

Convert NER column JSON to List datatype¶

Make Feature No_of_Steps_to_make_recipe¶

Make Feature No_of_ingredients_in_recipe¶

Sort Data by Number of Ingredeints¶

Sort Data by No_of_Steps_to_make_recipe¶

Data Quality Checks¶

(1) - Missing Values Analysis¶

(2) - Check Data Types¶

(3) - Check Unique Values¶

(4) - Boxplot Analysis/ Outlier Detection¶

Lets Analyze Max number of ingredients recipe¶

Issue with Textual Data¶

Exploratory Data Analysis (EDA)¶

Importance of Ingredients¶

Identify All Ingredients Used¶

Word Cloud Analysis of Recipes¶

Top/ Important Recipes¶

Top/ Important Ingredients/ Units/ Quantities¶

Top/ Important Directions Words¶

Top/ Important Words in NER¶

For 100 common ingredients¶

Pick 20 common ingredients¶

Network Analysis of Ingredients¶

Recipe Recommendation based on Ingredients¶

Calculate TF=IDF of the recipes Ingredients¶

Find Cosine Similarity Matrix¶

Recommed Similar Recipes to Sweet Potatoes Casserole¶

Recommed Similar Recipes to Creamy Corn¶

Which Recipe I can make?¶

Show Recipe for available Ingredients¶

Generative AI for Directions Generation¶

How System Work?¶

Example 2¶

Clustering or Grouping of Recipes¶

	title	ingredients	directions	link	source	NER	site
0	No-Bake Nut Cookies	["1 c. firmly packed brown sugar", "1/2 c. eva...	["In a heavy 2-quart saucepan, mix brown sugar...	www.cookbooks.com/Recipe-Details.aspx?id=44874	Gathered	["bite size shredded rice biscuits", "vanilla"...	www.cookbooks.com
1	Jewell Ball'S Chicken	["1 small jar chipped beef, cut up", "4 boned ...	["Place chipped beef on bottom of baking dish....	www.cookbooks.com/Recipe-Details.aspx?id=699419	Gathered	["cream of mushroom soup", "beef", "sour cream...	www.cookbooks.com
2	Creamy Corn	["2 (16 oz.) pkg. frozen corn", "1 (8 oz.) pkg...	["In a slow cooker, combine all ingredients. C...	www.cookbooks.com/Recipe-Details.aspx?id=10570	Gathered	["frozen corn", "pepper", "cream cheese", "gar...	www.cookbooks.com
3	Chicken Funny	["1 large whole chicken", "2 (10 1/2 oz.) cans...	["Boil and debone chicken.", "Put bite size pi...	www.cookbooks.com/Recipe-Details.aspx?id=897570	Gathered	["chicken gravy", "cream of mushroom soup", "c...	www.cookbooks.com
4	Reeses Cups(Candy)	["1 c. peanut butter", "3/4 c. graham cracker ...	["Combine first four ingredients and press in ...	www.cookbooks.com/Recipe-Details.aspx?id=659239	Gathered	["graham cracker crumbs", "powdered sugar", "p...	www.cookbooks.com

	title	ingredients	directions	link	source	NER	site	No_of_Steps_to_make_recipe
0	No-Bake Nut Cookies	["1 c. firmly packed brown sugar", "1/2 c. eva...	[In a heavy 2-quart saucepan, mix brown sugar,...	www.cookbooks.com/Recipe-Details.aspx?id=44874	Gathered	[bite size shredded rice biscuits, vanilla, br...	www.cookbooks.com	6
1	Jewell Ball'S Chicken	["1 small jar chipped beef, cut up", "4 boned ...	[Place chipped beef on bottom of baking dish.,...	www.cookbooks.com/Recipe-Details.aspx?id=699419	Gathered	[cream of mushroom soup, beef, sour cream, chi...	www.cookbooks.com	3
2	Creamy Corn	["2 (16 oz.) pkg. frozen corn", "1 (8 oz.) pkg...	[In a slow cooker, combine all ingredients. Co...	www.cookbooks.com/Recipe-Details.aspx?id=10570	Gathered	[frozen corn, pepper, cream cheese, garlic pow...	www.cookbooks.com	1
3	Chicken Funny	["1 large whole chicken", "2 (10 1/2 oz.) cans...	[Boil and debone chicken., Put bite size piece...	www.cookbooks.com/Recipe-Details.aspx?id=897570	Gathered	[chicken gravy, cream of mushroom soup, chicke...	www.cookbooks.com	6
4	Reeses Cups(Candy)	["1 c. peanut butter", "3/4 c. graham cracker ...	[Combine first four ingredients and press in 1...	www.cookbooks.com/Recipe-Details.aspx?id=659239	Gathered	[graham cracker crumbs, powdered sugar, peanut...	www.cookbooks.com	3

	title	ingredients	directions	link	source	NER	site	No_of_Steps_to_make_recipe	No_of_ingredients_in_recipe
0	No-Bake Nut Cookies	[1 c. firmly packed brown sugar, 1/2 c. evapor...	[In a heavy 2-quart saucepan, mix brown sugar,...	www.cookbooks.com/Recipe-Details.aspx?id=44874	Gathered	[bite size shredded rice biscuits, vanilla, br...	www.cookbooks.com	6	6
1	Jewell Ball'S Chicken	[1 small jar chipped beef, cut up, 4 boned chi...	[Place chipped beef on bottom of baking dish.,...	www.cookbooks.com/Recipe-Details.aspx?id=699419	Gathered	[cream of mushroom soup, beef, sour cream, chi...	www.cookbooks.com	3	4
2	Creamy Corn	[2 (16 oz.) pkg. frozen corn, 1 (8 oz.) pkg. c...	[In a slow cooker, combine all ingredients. Co...	www.cookbooks.com/Recipe-Details.aspx?id=10570	Gathered	[frozen corn, pepper, cream cheese, garlic pow...	www.cookbooks.com	1	6
3	Chicken Funny	[1 large whole chicken, 2 (10 1/2 oz.) cans ch...	[Boil and debone chicken., Put bite size piece...	www.cookbooks.com/Recipe-Details.aspx?id=897570	Gathered	[chicken gravy, cream of mushroom soup, chicke...	www.cookbooks.com	6	5
4	Reeses Cups(Candy)	[1 c. peanut butter, 3/4 c. graham cracker cru...	[Combine first four ingredients and press in 1...	www.cookbooks.com/Recipe-Details.aspx?id=659239	Gathered	[graham cracker crumbs, powdered sugar, peanut...	www.cookbooks.com	3	5

	title	ingredient
0	No-Bake Nut Cookies	bite size shredded rice biscuits
0	No-Bake Nut Cookies	vanilla
0	No-Bake Nut Cookies	brown sugar
0	No-Bake Nut Cookies	nuts
0	No-Bake Nut Cookies	milk
...	...	...
2231141	Polpette in Spicy Tomato Sauce	tomato sauce
2231141	Polpette in Spicy Tomato Sauce	garlic
2231141	Polpette in Spicy Tomato Sauce	sausage
2231141	Polpette in Spicy Tomato Sauce	bread crumbs
2231141	Polpette in Spicy Tomato Sauce	salt

Load Python Libraries Here¶

Read Dataset¶

What fields are in the data?¶

How do fields in the data relate to each other?¶

Convert NER column JSON to List datatype¶

Make Feature No_of_Steps_to_make_recipe¶

Make Feature No_of_ingredients_in_recipe¶

Sort Data by Number of Ingredeints¶

Sort Data by No_of_Steps_to_make_recipe¶

Data Quality Checks¶

(1) - Missing Values Analysis¶

(2) - Check Data Types¶

(3) - Check Unique Values¶

(4) - Boxplot Analysis/ Outlier Detection¶

Lets Analyze Max number of ingredients recipe¶

Issue with Textual Data¶

Exploratory Data Analysis (EDA)¶

Importance of Ingredients¶

Identify All Ingredients Used¶

Word Cloud Analysis of Recipes¶

Top/ Important Recipes¶

Top/ Important Ingredients/ Units/ Quantities¶

Top/ Important Directions Words¶

Top/ Important Words in NER¶

For 100 common ingredients¶

Pick 20 common ingredients¶

Network Analysis of Ingredients¶

Recipe Recommendation based on Ingredients¶

Calculate TF=IDF of the recipes Ingredients¶

Find Cosine Similarity Matrix¶

System will recommend Top N recipes based on ingredients similarity¶

Recommed Similar Recipes to Sweet Potatoes Casserole¶

Recommed Similar Recipes to Creamy Corn¶

Which Recipe I can make?¶

Show Recipe for available Ingredients¶

Recommend Recipe for Ingredients¶

Generative AI for Directions Generation¶

How System Work?¶

Example 2¶

Clustering or Grouping of Recipes¶